Discussion of article "Exploring Seasonal Patterns of Financial Time Series with Boxplot" - page 32
You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
will have nothing to do with seasonal patterns.
I don't understand that term.
Found a relationship between the behaviour of non-overlapping intervals within a day. The relationship has been tested on OOS. What you call it doesn't matter.
I don't understand that term.
Found a relationship between the behaviour of non-overlapping intervals within a day. The correlation has been tested on OOS. It doesn't matter what you call it.
Check it on the 3rd independent subsample, then you can assume you've found something, not an OOS fit.
Otherwise the curves could overlap by accident and give a high kc.
just like in MO - traine subsample, validation subsample and test independent subsample. It is desirable that they do not follow each other strictly in time
I have a problem when I run this code
AttributeError: 'Int64Index' object has no attribute 'year'
How can i solve them?
Thanks for the useful codes.
I wrote a Python code. Can I run it in Meta Tester Strategy?
I tried getting the hourly data from mt5 in vain. Yet I am easily able to get Daily, weekly and monthly data? Any rason why Maxim?
Hi, I think some changes in MT5 python api, so need to change code. Later Ill fix it.
Hi Maxim,
I run code:
rates = pd.DataFrame(mt5.copy_rates_range("EURUSD", mt5.TIMEFRAME_D1, datetime(2010, 1, 1), datetime(2020, 1, 1)),
columns=['time', 'open', 'low', 'high', 'close', 'tick_volume', 'spread', 'real_volume'])
and the time I get is sth like '1262563200' which does not make sense, How can this be fixed plz?
Thx!